Object recognition systems that deconstruct images into ever smaller elements should be much more efficient and may yield insights on brain behavior, and underlying such systems are new methods developed by researchers at the Massachusetts Institute of Technology (MIT) and the University of California, Los Angeles (UCLA). The researchers have developed a system that learns to recognize new objects by being “trained” with digital images of labeled objects. For each labeled item, the system first identifies the smallest elements, and then seeks instances in which these elements are interconnected into slightly more complex configurations. The system continues to search for instances in which shapes of ever increasing sophistication are linked together until it has put together a hierarchical catalog of increasingly complex components whose top layer is a model of the entire object. The system then sifts through its catalog from the top down, weeding out all redundancies. Memory is saved because different objects can have shapes in common, requiring only once instance of memory storage.
View Full Article
For More Information Visit: http://www.cpccci.com

European researchers working on the INTAMAP project have developed a statistical tool that can turn a set of point measurements into a contour map that can be published on the Web in real time. The INTAMAP project, led by University of Munster’s Edzer Pebesma, uses a process called interpolation to find the value of an environmental variable at a point on a map where there is no monitoring device. The system creates a contour map that shows what is happening between the measurement points and describes how accurate those measurements are. The open source interpolation software accepts raw data published on the Web using standards developed by the Open Geospatial Consortium (OGC). INTAMAP analyzes the data and conforms to OGC standards to create maps automatically, display them on the Web, and update them as needed. Pebesma says the INTAMAP tools could help researchers study weather patterns, groundwater pollution, agriculture, medical imaging, and other areas where a two-dimensional picture needs to be created from a series of point readings.
View Full Article
For More Information Visit: http://www.cpccci.com